Information processing apparatus, information processing method, and information processing program

Abstract

To efficiency search for an object associated with a sensed event, an information processing apparatus includes a sensor that analyzes a captured video and senses whether a predetermined event has occurred, a determining unit that determines a type of an object to be used as query information based on a type of the event in response to sensing of the event occurrence, and a generator that detects the object of the determined type from the video and generates the query information based on the detected object.

The invention claimed is: 
     
       1. An information processing system comprising:
 one or more memories that store: 
 a database storing surveillance videos; and 
 program instructions; and 
 one or more processors configured to read the program instructions to:
 extract a first upper feature, from an upper body of a target person in a first image in a captured surveillance video, and a first lower feature from a lower body of the target person in the first image; 
 search, based on the first upper and lower features to each of second upper and lower features which are extracted from upper and lower bodies of a reference person in at least one of second images in surveillance videos stored in the database, for a target image including the target person from among the second images; and 
 output the target image and a first location which is determined based on a location of a camera that captured the target image, 
 
 wherein a fall alert is set to be issued when a person has fallen down and remained immovable for a preliminary time, and 
 wherein an object related to a fallen person is extracted from an image going back a longer time than the preliminary time. 
 
     
     
       2. The information processing system according to  claim 1 , wherein the one or more processors read the program instructions to further:
 output a similarity between each of first features, comprising the first upper feature and the first lower feature, and each of second features, comprising the second upper feature and the second lower feature, the similarity corresponding to each of parts of the target person. 
 
     
     
       3. The information processing system according to  claim 2 , wherein the one or more processors read the program instructions further to display the similarity. 
     
     
       4. The information processing system according to  claim 1 , wherein the one or more processors read the program instructions further to:
 detect a predetermined action in the captured surveillance video, using a detector; 
 output an alert information including a type of the predetermined action when the predetermined action is detected; and 
 output the first features with the alert information. 
 
     
     
       5. An information processing method comprising:
 storing a database storing surveillance videos; 
 extracting a first upper feature from an upper body of a target person in a first image in a captured surveillance video, and a first lower feature from a lower body of the target person in the first image; 
 search, based on the first upper and lower features to each of second upper and lower features which are extracted from upper and lower bodies of a reference person in at least one of second images in surveillance videos stored in the database, for a target image including the target person from among the second images; and 
 outputting the target image and a first location which is determined based on a location of a camera that captured the target image, 
 wherein a fall alert is set to be issued when a person has fallen down and remained immovable for a preliminary time, and 
 wherein an object related to a fallen person is extracted from an image going back a longer time than the preliminary time. 
 
     
     
       6. The information processing method according to  claim 5 , further comprising:
 outputting a similarity between each of first features, comprising the first upper feature and the first lower feature, and each of the second features, comprising the second upper feature and the second lower feature, the similarity corresponding to each of parts of the target person. 
 
     
     
       7. The information processing method according to  claim 6 , further comprising:
 displaying the similarity. 
 
     
     
       8. The information processing system according to  claim 6 ,
 wherein the first features further comprise at least one of a plurality of belongings of the target person; and 
 wherein the second features further comprise at least one of a plurality of belongings of the reference person. 
 
     
     
       9. The information processing method according to  claim 5 , further comprising:
 detecting a predetermined action in the captured surveillance video, using a detector; and 
 outputting an alert information including a type of the predetermined action when the predetermined action is detected; and 
 outputting the first features with the alert information. 
 
     
     
       10. A non-transitory computer readable medium storing an information processing program for causing a computer to execute:
 storing a database storing surveillance videos; 
 extracting a first upper feature, from an upper body of a target person in a first image in a captured surveillance video, and a first lower feature from a lower body of the target person in the first image; 
 search, based on the first upper and lower features to each of second upper and lower features which are extracted from upper and lower bodies of a reference person in at least one of second images in surveillance videos stored in the database, for a target image including the target person from among the second images; and 
 outputting the target image and a first location which is determined based on a location of a camera that captured the target image, 
 wherein a fall alert is set to be issued when a person has fallen down and remained immovable for a preliminary time, and 
 wherein an object related to a fallen person is extracted from an image going back a longer time than the preliminary time. 
 
     
     
       11. The non-transitory computer readable medium according to  claim 10  storing the information processing program for further causing a computer to execute:
 outputting a similarity between each of first features, comprising the first upper feature and the first lower feature, and each of the second features, comprising the second upper feature and the second lower feature, the similarity corresponding to each of parts of the target person. 
 
     
     
       12. The non-transitory computer readable medium according to  claim 11  storing the information processing program for further causing a computer to execute, further comprising:
 displaying the similarity. 
 
     
     
       13. The non-transitory computer readable medium according to  claim 11  storing the information processing program for further causing a computer to execute, further comprising:
 detecting a predetermined action in the captured surveillance video, using a detector; 
 outputting an alert information including a type of the predetermined action when the predetermined action is detected; and 
 outputting the first features with the alert information.